Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 190 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1606. Min Act: -0.0001

Data Index: 259678 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1457. Min Act: -0.0001

Data Index: 949396 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1488. Min Act: -0.0001

Data Index: 981914 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1320. Min Act: -0.0000

Data Index: 5439 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1498. Min Act: -0.0001

Data Index: 1099328 (C4 (Web Text))

Max Activating Token Index: 673

Text #5

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1395. Min Act: -0.0001

Data Index: 380418 (C4 (Web Text))

Max Activating Token Index: 213

Text #6

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1429. Min Act: -0.0001

Data Index: 1259237 (C4 (Web Text))

Max Activating Token Index: 768

Text #7

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1316. Min Act: -0.0000

Data Index: 582363 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1322. Min Act: -0.0001

Data Index: 308681 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1315. Min Act: -0.0000

Data Index: 814210 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1393. Min Act: -0.0001

Data Index: 580916 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1313. Min Act: -0.0001

Data Index: 16593 (C4 (Web Text))

Max Activating Token Index: 64

Text #12

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1270. Min Act: -0.0001

Data Index: 114894 (C4 (Web Text))

Max Activating Token Index: 639

Text #13

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1328. Min Act: -0.0001

Data Index: 823489 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1269. Min Act: -0.0001

Data Index: 462703 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1248. Min Act: -0.0001

Data Index: 541984 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1286. Min Act: -0.0001

Data Index: 487227 (C4 (Web Text))

Max Activating Token Index: 879

Text #17

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1156. Min Act: -0.0001

Data Index: 965187 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1083. Min Act: -0.0000

Data Index: 1007790 (C4 (Web Text))

Max Activating Token Index: 338

Text #19

Max Range: 0.1606. Min Range: -0.1606

Max Act: 0.1119. Min Act: -0.0001

Data Index: 1036888 (C4 (Web Text))

Max Activating Token Index: 547